European Cooperative Acute Stroke Study II Research Articles

A weakly supervised deep learning model integrating noncontrasted computed tomography images and clinical factors facilitates haemorrhagic transformation prediction after intravenous thrombolysis in acute ischaemic stroke patients

BackgroundHaemorrhage transformation (HT) is a serious complication of intravenous thrombolysis (IVT) in acute ischaemic stroke (AIS). Accurate and timely prediction of the risk of HT before IVT may change the treatment decision and improve clinical prognosis. We aimed to develop a deep learning method for predicting HT after IVT for AIS using noncontrast computed tomography (NCCT) images.MethodsWe retrospectively collected data from 828 AIS patients undergoing recombinant tissue plasminogen activator (rt-PA) treatment within a 4.5-h time window (n = 665) or of undergoing urokinase treatment within a 6-h time window (n = 163) and divided them into the HT group (n = 69) and non-HT group (n = 759). HT was defined based on the criteria of the European Cooperative Acute Stroke Study-II trial. To address the problems of indiscernible features and imbalanced data, a weakly supervised deep learning (WSDL) model for HT prediction was constructed based on multiple instance learning and active learning using admission NCCT images and clinical information in addition to conventional deep learning models. Threefold cross-validation and transfer learning were performed to confirm the robustness of the network. Of note, the predictive value of the commonly used scales in clinics associated with NCCT images (i.e., the HAT and SEDAN score) was also analysed and compared to measure the feasibility of our proposed DL algorithms.ResultsCompared to the conventional DL and ML models, the WSDL model had the highest AUC of 0.799 (95% CI 0.712–0.883). Significant differences were observed between the WSDL model and five ML models (P < 0.05). The prediction performance of the WSDL model outperforms the HAT and SEDAN scores at the optimal operating point (threshold = 1.5). Further subgroup analysis showed that the WSDL model performed better for symptomatic intracranial haemorrhage (AUC = 0.833, F1 score = 0.909).ConclusionsOur WSDL model based on NCCT images had relatively good performance for predicting HT in AIS and may be suitable for assisting in clinical treatment decision-making.

Prediction of Hemorrhagic Transformation after Ischemic Stroke Using Machine Learning.

Hemorrhagic transformation (HT) is one of the leading causes of a poor prognostic marker after acute ischemic stroke (AIS). We compared the performances of the several machine learning (ML) algorithms to predict HT after AIS using only structured data. A total of 2028 patients with AIS, who were admitted within seven days of symptoms onset, were included in this analysis. HT was defined based on the criteria of the European Co-operative Acute Stroke Study-II trial. The whole dataset was randomly divided into a training and a test dataset with a 7:3 ratio. Binary logistic regression, support vector machine, extreme gradient boosting, and artificial neural network (ANN) algorithms were used to assess the performance of predicting the HT occurrence after AIS. Five-fold cross validation and a grid search technique were used to optimize the hyperparameters of each ML model, which had its performance measured by the area under the receiver operating characteristic (AUROC) curve. Among the included AIS patients, the mean age and number of male subjects were 69.6 years and 1183 (58.3%), respectively. HT was observed in 318 subjects (15.7%). There were no significant differences in corresponding variables between the training and test dataset. Among all the ML algorithms, the ANN algorithm showed the best performance in terms of predicting the occurrence of HT in our dataset (0.844). Feature scaling including standardization and normalization, and the resampling strategy showed no additional improvement of the ANN’s performance. The ANN-based prediction of HT after AIS showed better performance than the conventional ML algorithms. Deep learning may be used to predict important outcomes for structured data-based prediction.

A Nomogram to Predict Symptomatic Intracranial Hemorrhage After Intravenous Thrombolysis in Chinese Patients

Background and AimsA reliable predictive score system to identify the risk of symptomatic intracranial hemorrhage (sICH) after intravenous thrombolysis (IVT) in acute ischemic stroke patients is of great essence. We aimed to develop a nomogram for predicting the risk of sICH after IVT in Chinese patients.MethodsWe recruited acute ischemic stroke patients who were treated with IVT from five advanced stroke centers in China from April 2014 to November 2020. sICH was diagnosed according to the European Cooperative Acute Stroke Study II (ECASS-II) definition. Multivariable logistic regression was performed to construct the best-fit nomogram. The discrimination and calibration of the nomogram were evaluated by the area under the receiver operating characteristic curve (AUC-ROC) and calibration plot.ResultsA total of 1200 patients were enrolled, of whom 66 (5.5%) developed sICH. In the multivariate logistic regression model, atrial fibrillation (odds ratio [OR] 3.25; 95% confidence interval [CI], 1.89−5.60; P < 0.001), baseline glucose level (OR, 1.13; 95% CI, 1.07−1.20; P < 0.001), neutrophil to lymphocyte ratio (OR, 1.05; 95% CI, 1.01−1.09; P = 0.024) and baseline National Institute of Health Stroke Scale (NIHSS) (OR, 1.07; 95% CI, 1.04−1.10; P < 0.001) were independent predictors for sICH and were used to generate the nomogram. The nomogram demonstrated good discrimination as the AUC-ROC value was 0.788 (95% CI, 0.737–0.840). The calibration plot revealed good calibration.ConclusionThe nomogram consisted of atrial fibrillation, baseline glucose level, neutrophil to lymphocyte ratio, and NIHSS score may predict the risk of sICH in Chinese acute ischemic stroke patients treated with IVT.

Systemic arterial blood pressure and intracerebral hemorrhage after mechanical thrombectomy in anterior cerebral circulation

The relationship between systemic arterial blood pressure (BP) and intracerebral hemorrhage (ICH) after mechanical thrombectomy (MT) of the cerebral artery remains unclear. This study aimed to determine the effect of...

Matrix Metalloproteinase-9 Relationship With Infarct Growth and Hemorrhagic Transformation in the Era of Thrombectomy.

Objective: To assess the relationship between matrix metalloproteinase 9 (MMP-9), a proteolytic enzyme involved in the breakdown of the blood-brain barrier, and infarct growth and hemorrhagic transformation in acute ischemic stroke (AIS) with large vessel occlusion (LVO) in the era of mechanical thrombectomy (MT) using the kinetics of MMP-9 and sequential magnetic resonance imaging (MRI).Methods: HIBISCUS-STROKE is a cohort study including AIS patients with LVO treated with MT following admission MRI. Patients underwent sequential assessment of MMP-9, follow-up CT at day 1, and MRI at day 6. The CT scan at day 1 classified any hemorrhagic transformation according to the European Co-operative Acute Stroke Study-II (ECASS II) classification. Infarct growth was defined as the difference between final Fluid-Attenuated Inversion Recovery volume and baseline diffusion-weighted imaging volume. Conditional logistic regression analyses were adjusted for main confounding variables including reperfusion status.Results: One hundred and forty-eight patients represent the study population. A high MMP-9 level at 6 h from admission (H6) (p = 0.02), a high glucose level (p = 0.01), a high temperature (p = 0.04), and lack of reperfusion (p = 0.02) were associated with infarct growth. A high MMP-9 level at H6 (p = 0.03), a high glucose level (p = 0.03) and a long delay from symptom onset to groin puncture (p = 0.01) were associated with hemorrhagic transformation.Conclusions: In this MT cohort study, MMP-9 level at H6 predicts infarct growth and hemorrhagic transformation.

Safety of Intravenous Thrombolysis Among Patients Taking Direct Oral Anticoagulants: A Systematic Review and Meta-Analysis.

Background and Purpose- There are scarce data regarding the safety of intravenous thrombolysis (IVT) in acute ischemic stroke among patients on direct oral anticoagulants (DOACs). Methods- We performed a systematic review and meta-analysis of the current literature. Data regarding all adult patients pretreated with DOAC who received IVT for acute ischemic stroke were recorded. Meta-analysis was performed by comparing the rate of symptomatic intracerebral hemorrhage in these patients with (1) stroke patients without prior anticoagulation therapy and (2) patients on warfarin with international normalized ratio <1.7. Meta-analyses were further conducted in subgroups as follows: (1) administration of DOAC within 48 hours versus an unknown interval before IVT, (2) consideration of symptomatic intracerebral hemorrhage outcome according to the National Institute of Neurological Disorders (NINDS) versus the European Cooperative Acute Stroke Study II (ECASS-II) criteria. Results- After reviewing 13 392 reports and communicating with certain authors of 12 published studies, a total of 52 823 acute ischemic stroke patients from 6 studies were enrolled in the present meta-analysis: DOACs: 366, warfarin: 2133, and 503 241 patients without prior anticoagulation. We detected no additional risk of symptomatic intracerebral hemorrhage following IVT among patients taking DOACs within 48 hours-DOACs-warfarin: NINDS (odds ratio [OR], 0.55 [95% CI, 0.19-1.59]), ECASS-II (OR, 0.77 [95% CI, 0.28-2.16]); DOACs-no-anticoagulation: NINDS (OR, 1.23 [95% CI, 0.46-3.31]), ECASS-II (OR, 0.87 [95% CI, 0.32-2.41]). Similarly, no additional risk was detected with no time limit between last DOAC intake-DOACs warfarin: NINDS (OR, 0.85 [95% CI, 0.49-1.45]), ECASS-II (OR, 1.11 [95% CI, 0.67-1.85]); DOACs-no-anticoagulation: NINDS (OR, 1.17 [95% CI, 0.43-3.15]), ECASS-II (OR, 0.87 [95% CI, 0.33-2.41]). There was no evidence of heterogeneity across included studies (I2=0%). We also provided the details of 123 individual cases with or without reversal agents before IVT. There was no significant increase in the risk of hemorrhagic transformation (OR, 1.48 [95% CI, 0.50-4.38]), symptomatic hemorrhagic transformation (OR, 0.47 [95% CI, 0.09-2.55]), or early mortality (OR, 0.60 [95% CI, 0.11-3.43]) between cohorts who did or did not receive prethrombolysis idarucizumab. Conclusions- The results of our study indicated that prior intake of DOAC appears not to increase the risk of symptomatic intracerebral hemorrhage in selected AIS patients treated with IVT.

Post-thrombolytic blood pressure and symptomatic intracerebral hemorrhage.

Most guidelines for intravenous thrombolysis (IVT) in acute ischaemic stroke patients advise keeping systolic blood pressure (BP) below 180/105 mmHg prior to the bolus injection. Less is known about optimal management of BP thereafter. We assessed temporal changes in post-thrombolytic systolic BP values and their impact on development of symptomatic intracerebral hemorrhage (sICH). The study cohort included 1868 consecutive acute ischaemic stroke patients treated with IVT at the Helsinki University Central Hospital. sICH was defined according to the European Cooperative Acute Stroke Study II (ECASS-II) (primary outcome), National Institute of Neurological Disorders and Stroke, and Safe Implementation of Thrombolysis in Stroke criteria. We evaluated BP at admission, prior to IVT and at 2, 4, 8, 12, 24 and 48 h after thrombolysis. We used univariate and multivariable models to test the effect of BP at various time-points on development of post-thrombolytic sICH. Prevalence of sICH in the cohort was 5.8% (ECASS-II). Patients with sICH had significantly higher systolic BP at several time-points after IVT compared with those without sICH (P < 0.01 at 2 and 4 h; P < 0.05 at 12 and 48 h). The odds ratios for development of sICH per 10 mmHg increase in BP were 1.14 [95% confidence interval (CI), 1.03-1.25], 1.14 (95% CI, 1.03-1.25), 1.12 (95% CI, 1.01-1.23) and 1.12 (95% CI, 1.01-1.23), respectively. At 8 h, we observed a trend (P = 0.07) for ECASS-II and a significant effect (P < 0.05) for National Institute of Neurological Disorders and Stroke, and Safe Implementation of Thrombolysis in Stroke criteria. Thus, the only time-point with no difference observed was 24 h. Patients with post-thrombolytic sICH have significantly higher systolic BP at several time-points compared with patients without sICH.

Risk of Symptomatic Intracerebral Hemorrhage After Intravenous Thrombolysis in Patients With Acute Ischemic Stroke and High Cerebral Microbleed Burden: A Meta-analysis.

Cerebral microbleeds (CMBs) have been established as an independent predictor of cerebral bleeding. There are contradictory data regarding the potential association of CMB burden with the risk of symptomatic intracerebral hemorrhage (sICH) in patients with acute ischemic stroke (AIS) treated with intravenous thrombolysis (IVT). To investigate the association of high CMB burden (>10 CMBs on a pre-IVT magnetic image resonance [MRI] scan) with the risk of sICH following IVT for AIS. Eligible studies were identified by searching Medline and Scopus databases. No language or other restrictions were imposed. The literature search was conducted on October 7, 2015. This meta-analysis has adopted the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and was written according to the Meta-analysis of Observational Studies in Epidemiology (MOOSE) proposal. Eligible prospective study protocols that reported sICH rates in patients with AIS who underwent MRI for CMB screening prior to IVT. The reported rates of sICH complicating IVT in patients with AIS with pretreatment MRI were extracted independently for groups of patients with 0 CMBs (CMB absence), 1 or more CMBs (CMB presence), 1 to 10 CMBs (low to moderate CMB burden), and more than 10 CMBs (high CMB burden). An individual-patient data meta-analysis was also performed in the included studies that provided complete patient data sets. Symptomatic intracerebral hemorrhage based on the European Cooperative Acute Stroke Study-II definition (any intracranial bleed with ≥4 points worsening on the National Institutes of Health Stroke Scale score). We included 9 studies comprising 2479 patients with AIS. The risk of sICH after IVT was found to be higher in patients with evidence of CMB presence, compared with patients without CMBs (risk ratio [RR], 2.36; 95% CI, 1.21-4.61; P = .01). A higher risk for sICH after IVT was detected in patients with high CMB burden (>10 CMBs) when compared with patients with 0 to 10 CMBs (RR, 12.10; 95% CI, 4.36-33.57; P < .001) or 1 to 10 CMBs (RR, 7.01; 95% CI, 3.20-15.38; P < .001) on pretreatment MRI. In the individual-patient data meta-analysis, high CMB burden was associated with increased likelihood of sICH before (unadjusted odds ratio, 31.06; 95% CI, 7.12-135.44; P < .001) and after (adjusted odds ratio, 18.17; 95% CI, 2.39-138.22; P = .005) adjusting for potential confounders. Presence of CMB and high CMB burdens on pretreatment MRI were independently associated with sICH in patients with AIS treated with IVT. High CMB burden may be included in individual risk stratification scores predicting sICH risk following IVT for AIS.

Recanalization therapies in acute ischemic stroke patients: impact of prior treatment with novel oral anticoagulants on bleeding complications and outcome.

We explored the safety of intravenous thrombolysis (IVT) or intra-arterial treatment (IAT) in patients with ischemic stroke on non-vitamin K antagonist oral anticoagulants (NOACs, last intake <48 hours) in comparison with patients (1) taking vitamin K antagonists (VKAs) or (2) without previous anticoagulation (no-OAC). This is a multicenter cohort pilot study. Primary outcome measures were (1) occurrence of intracranial hemorrhage (ICH) in 3 categories: any ICH (ICHany), symptomatic ICH according to the criteria of the European Cooperative Acute Stroke Study II (ECASS-II) (sICHECASS-II) and the National Institute of Neurological Disorders and Stroke (NINDS) thrombolysis trial (sICHNINDS); and (2) death (at 3 months). Cohorts were compared by using propensity score matching. Our NOAC cohort comprised 78 patients treated with IVT/IAT and the comparison groups of 441 VKA patients and 8938 no-OAC patients. The median time from last NOAC intake to IVT/IAT was 13 hours (interquartile range, 8-22 hours). In VKA patients, median pre-IVT/IAT international normalized ratio was 1.3 (interquartile range, 1.1-1.6). ICHany was observed in 18.4% NOAC patients versus 26.8% in VKA patients and 17.4% in no-OAC patients. sICHECASS-II and sICHNINDS occurred in 2.6%/3.9% NOAC patients, in comparison with 6.5%/9.3% of VKA patients and 5.0%/7.2% of no-OAC patients, respectively. At 3 months, 23.0% of NOAC patients in comparison with 26.9% of VKA patients and 13.9% of no-OAC patients had died. Propensity score matching revealed no statistically significant differences. IVT/IAT in selected patients with ischemic stroke under NOAC treatment has a safety profile similar to both IVT/IAT in patients on subtherapeutic VKA treatment or in those without previous anticoagulation. However, further prospective studies are needed, including the impact of specific coagulation tests.

Administration of Free Radical Scavenger Edaravone Associated With Higher Frequency of Hemorrhagic Transformation in Patients With Cardiogenic Embolism

Free radicals are known to activate coagulation and inhibit fibrinolysis. Edaravone, a free radical scavenger, protects vascular endothelial cells and neurons during acute brain ischemia in in vitro models. Hemorrhagic transformation and treatment outcomes were retrospectively examined in 76 patients with acute cardiogenic embolism treated with edaravone in addition to routine treatment within 24 hours of the onset of symptoms. Hemorrhagic transformation was categorized according to European Cooperative Acute Stroke Study-II. Patient characteristics were also evaluated, including evidence of hypertension, diabetes mellitus, hyperlipidemia, coronary heart disease, history of smoking, National Institutes of Health Stroke Scale on arrival, and modified Rankin scale at 3 months post-onset. Edaravone administration was one of the factors that contributed to increased frequency of hemorrhagic transformation, but had showed no significant relationship with the outcome. The present study showed that edaravone administration increased the frequency of hemorrhagic transformation with heparin in patients with cardiogenic embolism. Free radical scavenging may have promoted the coagulating conditions. Edaravone administration may allow reduction of the dose of heparin and tissue plasminogen activator in patients with acute ischemic stroke.